Related papers: AdaGen: Learning Adaptive Policy for Image Synthes…

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

We propose a computationally-friendly adaptive learning rate schedule, "AdaLoss", which directly uses the information of the loss function to adjust the stepsize in gradient descent methods. We prove that this schedule enjoys linear…

Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and…

Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed as two major strategies. However, both approaches have…

The increasing reliance on large-scale datasets in machine learning poses significant privacy and ethical challenges, particularly in sensitive domains such as face recognition. Synthetic data generation offers a promising alternative;…

Visuomotor policies have shown great promise in robotic manipulation but often require substantial amounts of human-collected data for effective performance. A key reason underlying the data demands is their limited spatial generalization…

Masked Generative Image Transformers (MaskGIT) have emerged as a scalable and efficient image generation framework, able to deliver high-quality visuals with low inference costs. However, MaskGIT's token unmasking scheduler, an essential…

The task of image generation started to receive some attention from artists and designers to inspire them in new creations. However, exploiting the results of deep generative models such as Generative Adversarial Networks can be long and…

Predictive simulations are essential for applications ranging from weather forecasting to material design. The veracity of these simulations hinges on their capacity to capture the effective system dynamics. Massively parallel simulations…

Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use…

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter…

Long video understanding is heavily bottlenecked by a rigid one-shot paradigm: existing methods either densely encode videos at prohibitive memory and latency costs, or aggressively compress them into sparse frame sets that irreversibly…

We introduce MDSGen, a novel framework for vision-guided open-domain sound generation optimized for model parameter size, memory consumption, and inference speed. This framework incorporates two key innovations: (1) a redundant video…

Although the capacity of deep generative models for image generation, such as Diffusion Models (DMs) and Generative Adversarial Networks (GANs), has dramatically improved in recent years, much of their success can be attributed to…

Deep learning classifiers face significant challenges when dealing with heterogeneous multi-modal and multi-organ biomedical datasets. The low-level feature distinguishability limited to imaging-modality hinders the classifiers' ability to…

Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notable redundancy in their computation: when sampling discrete…

Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to prevent forgetting previously learned classes include…

With the rapid development of AIGC technologies, generative image steganography has attracted increasing attention due to its high imperceptibility and flexibility. However, existing generative steganography methods often maintain…

Generating robot demonstrations through simulation is widely recognized as an effective way to scale up robot data. Previous work often trained reinforcement learning agents to generate expert policies, but this approach lacks sample…

Stochastic gradient decent~(SGD) and its variants, including some accelerated variants, have become popular for training in machine learning. However, in all existing SGD and its variants, the sample size in each iteration~(epoch) of…